Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    25

    np_max-act · gemini-2.0-flash

    This neuron detects numeric tokens representing age values in demographic breakdowns.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     españ
    -0.07
     jan
    -0.06
     arc
    -0.06
     infantry
    -0.06
    拜
    -0.06
    _constraint
    -0.06
    اصر
    -0.06
     Thumb
    -0.06
     enticing
    -0.06
    entimes
    -0.06
    POSITIVE LOGITS
    ξης
    0.08
     steht
    0.07
     чит
    0.06
     thẳng
    0.06
    ська
    0.06
    Vertices
    0.06
     keywords
    0.06
    [col
    0.06
    势
    0.06
    -mobile
    0.06
    Act Density 0.001%

    No Known Activations